RVC Tutorial: How to make your own AI voice model

Hi everyone, I'm Avera Yuki and in today's video I'll be showing you step by step how to make any AI voice model using the RVC and by the way I hope you don't mind if I use vocaloids' voice It's a vocaloid channel after all Okay first. Let me explain what the RVC is RVC or Retrieval-based Voice Conversion is a technique that uses a deep neural network to transform the voice of a speaker into another voice into another voice So simply put, if you already have an AI model created you can convert any voice into that model's voice which is what I am doing right now . Ok cool And now the next question: How to create such a voice model ? There are two ways I know but I will only show you the easier way The first thing you will need to do is to create a ''dataset'' folder This ''dataset'' should contain voice samples of the model you want to create All of those samples have to be under 10 second long otherwise you might get an error during a learning process the quality is up to you because you are the one who can be creative and will make all the samples and will make all the samples Okay. Let's assume we've already made this dataset I'll call it MikuAItest . Now we just put it in a .zip file create a folder named ''dataset'' in our google drive and drag the .zip file into this folder and when it's uploaded we go to the training site (the link is in description) This is Google Colab site which allows anyone to write or use Python codes here and if any of you don't know what Python is , it's a programming language which will train our AI model here so the first step we'll do is connecting our account